Triple
T1549536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 09/27 |
E33055
|
entity |
| Predicate | hasChallengingTerrainOrObstacles |
P11058
|
FINISHED |
| Object | downtown buildings on approach |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: downtown buildings on approach | Statement: [Runway 09/27, hasChallengingTerrainOrObstacles, downtown buildings on approach]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChallengingTerrainOrObstacles Context triple: [Runway 09/27, hasChallengingTerrainOrObstacles, downtown buildings on approach]
-
A.
hasTrailDifficulty
Indicates the level of challenge or effort required to traverse a particular trail or route.
-
B.
terrainCapability
Indicates the types of terrain or ground conditions in which an entity can effectively operate or function.
-
C.
hasClimbingHazard
Indicates that something presents a risk or danger specifically associated with climbing activities.
-
D.
hasCliff
Indicates that something possesses or features a steep, high rock face or abrupt vertical drop as part of its structure or environment.
-
E.
isDifficultToAccessBecauseOf
chosen
Indicates that something is hard to reach, obtain, or use due to a specified obstacle, condition, or circumstance.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a885ee6db8819099502bc5ce8af881 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa574094048190a2d7fc3ac904d51e |
completed | March 6, 2026, 4:25 a.m. |
| PD | Predicate disambiguation | batch_69a907b426dc8190975c024a50955368 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.